Update app.py

app.py

@@ -4,31 +4,112 @@ import requests
 import inspect
 import pandas as pd
 
-# (Keep Constants as is)
+# 🔹 NOVO: imports do smolagents
+from smolagents import CodeAgent, InferenceClientModel
+
 # --- Constants ---
+# (mantido como no template)
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+
+# =========================================================
+#  Helper: limpeza de resposta para EXACT MATCH
+# =========================================================
+def clean_answer(text: str) -> str:
+    """
+    Limpa a saída do modelo para ficar mais adequada ao EXACT MATCH.
+    Remove prefixos como 'Answer:', 'Final answer:' etc.,
+    aspas externas e ponto final solto.
+    """
+    if text is None:
+        return ""
+
+    ans = str(text).strip()
+
+    # remove prefixos comuns
+    prefixes = [
+        "answer:", "resposta:", "final answer:", "final:", "ans:", "a:",
+        "the answer is", "the final answer is",
+    ]
+    lower = ans.lower()
+    for p in prefixes:
+        if lower.startswith(p):
+            ans = ans[len(p):].strip()
+            break
+
+    # remove ponto final se não parecer número decimal
+    if ans.endswith(".") and not ans.replace(".", "", 1).isdigit():
+        ans = ans[:-1].strip()
+
+    # remove aspas externas
+    if len(ans) > 1 and ans[0] == ans[-1] and ans[0] in ["'", '"']:
+        ans = ans[1:-1].strip()
+
+    return ans
+
+
+# =========================================================
+#  Basic Agent Definition – AGORA usando smolagents
+# =========================================================
+
+SYSTEM_PROMPT = (
+    "You are an exam-taking assistant.\n"
+    "For each question, reply with ONLY the final answer, with no explanation, "
+    "no reasoning, no extra words, no quotes, and no labels like 'Final answer'.\n"
+    "If the answer is a number, output just the number. "
+    "If it is a word or short phrase, output just that.\n"
+    "Your output will be compared to the ground truth using EXACT MATCH."
+)
+
+
 class BasicAgent:
+    """
+    Agente simples baseado em smolagents:
+    - Usa InferenceClientModel (Inference API da Hugging Face)
+    - Não utiliza tools adicionais
+    - Retorna uma string já limpa para EXACT MATCH
+    """
+
     def __init__(self):
-        print("BasicAgent initialized.")
+        print("Initializing smolagents BasicAgent...")
+
+        # Modelo remoto via Inference API (utiliza HF_TOKEN configurado no Space)
+        self.model = InferenceClientModel()
+
+        # CodeAgent sem ferramentas (agente simples)
+        self.agent = CodeAgent(
+            model=self.model,
+            tools=[],            # agente simples: sem tools
+            max_steps=1,         # sem tools, 1 passo é suficiente
+            system_prompt=SYSTEM_PROMPT,
+        )
+
     def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        print(f"Agent received question (first 80 chars): {question[:80]}...")
+        try:
+            raw_answer = self.agent.run(question)
+            fixed_answer = clean_answer(raw_answer)
+            print(f"Agent returning cleaned answer: {fixed_answer}")
+            return fixed_answer
+        except Exception as e:
+            print(f"Error inside BasicAgent.__call__: {e}")
+            # Em caso de erro, devolve string vazia (melhor do que quebrar tudo)
+            return ""
+
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+# =========================================================
+#  Runner + submit (mantido do template, só usando BasicAgent novo)
+# =========================================================
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
     Fetches all questions, runs the BasicAgent on them, submits all answers,
     and displays the results.
     """
     # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+    space_id = os.getenv("SPACE_ID")  # Get the SPACE_ID for sending link to the code
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -38,15 +119,17 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # 1. Instantiate Agent (agora nosso agente smolagents)
     try:
         agent = BasicAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
-    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
+
+    # In the case of an app running as a hugging Face space, this link points toward your codebase
+    # (useful for others so please keep it public)
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
+    print(f"Agent code URL: {agent_code}")
 
     # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
@@ -55,16 +138,16 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         response.raise_for_status()
         questions_data = response.json()
         if not questions_data:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", None
+            print("Fetched questions list is empty.")
+            return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
     except requests.exceptions.RequestException as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
     except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
+        print(f"Error decoding JSON response from questions endpoint: {e}")
+        print(f"Response text: {response.text[:500]}")
+        return f"Error decoding server response for questions: {e}", None
     except Exception as e:
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", None
@@ -81,19 +164,39 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             continue
         try:
             submitted_answer = agent(question_text)
-            answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+            answers_payload.append(
+                {"task_id": task_id, "submitted_answer": submitted_answer}
+            )
+            results_log.append(
+                {
+                    "Task ID": task_id,
+                    "Question": question_text,
+                    "Submitted Answer": submitted_answer,
+                }
+            )
         except Exception as e:
-             print(f"Error running agent on task {task_id}: {e}")
-             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+            print(f"Error running agent on task {task_id}: {e}")
+            results_log.append(
+                {
+                    "Task ID": task_id,
+                    "Question": question_text,
+                    "Submitted Answer": f"AGENT ERROR: {e}",
+                }
+            )
 
     if not answers_payload:
         print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
-    # 4. Prepare Submission 
-    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
+    # 4. Prepare Submission
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload,
+    }
+    status_update = (
+        f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
+    )
     print(status_update)
 
     # 5. Submit
@@ -142,19 +245,20 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# Basic Agent Evaluation Runner (smolagents)")
     gr.Markdown(
         """
         **Instructions:**
-
-        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
-        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
-        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
-
+        1.  This space uses a simple agent built with `smolagents` + `InferenceClientModel`.
+        2.  Log in to your Hugging Face account using the button below.
+        3.  Click **'Run Evaluation & Submit All Answers'** to fetch questions,
+            run the agent, submit answers, and see your score.
         ---
-        **Disclaimers:**
-        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
+        **Notes:**
+        - The correction on the server uses EXACT MATCH, so the agent is prompted
+          to output only the final answer (sem 'FINAL ANSWER', sem explicações).
+        - This template is intentionally simples; você pode adicionar tools,
+          melhorar o prompt, etc., se quiser subir seu score.
         """
     )
 
@@ -162,20 +266,24 @@ with gr.Blocks() as demo:
 
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
-    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+    status_output = gr.Textbox(
+        label="Run Status / Submission Result", lines=5, interactive=False
+    )
+    results_table = gr.DataFrame(
+        label="Questions and Agent Answers",
+        wrap=True,
+    )
 
     run_button.click(
         fn=run_and_submit_all,
-        outputs=[status_output, results_table]
+        outputs=[status_output, results_table],
     )
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
     # Check for SPACE_HOST and SPACE_ID at startup for information
     space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+    space_id_startup = os.getenv("SPACE_ID")  # Get SPACE_ID at startup
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -183,14 +291,16 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    if space_id_startup:  # Print repo URLs if SPACE_ID is found
         print(f"✅ SPACE_ID found: {space_id_startup}")
         print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
-        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
+        print(
+            f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main"
+        )
     else:
         print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+    print("-" * (60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)